def main(): global args set_random_seed(args.seed) if not args.use_avai_gpus: os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu_devices use_gpu = torch.cuda.is_available() if args.use_cpu: use_gpu = False log_name = 'log_test.txt' if args.evaluate else 'log_train.txt' sys.stdout = Logger(osp.join(args.save_dir, log_name)) print("==========\nArgs:{}\n==========".format(args)) if use_gpu: print("Currently using GPU {}".format(args.gpu_devices)) cudnn.benchmark = True else: print("Currently using CPU, however, GPU is highly recommended") print("Initializing image data manager") dm = ImageDataManager(use_gpu, **image_dataset_kwargs(args)) trainloader, testloader_dict = dm.return_dataloaders() print("Initializing model: {}".format(args.arch)) model = models.init_model(name=args.arch, num_classes=dm.num_train_pids, input_size=args.width, loss={'xent'}, use_gpu=use_gpu) print("Model size: {:.3f} M".format(count_num_param(model))) print(model) # sys.exit(0) criterion = CrossEntropyLoss(num_classes=dm.num_train_pids, use_gpu=use_gpu, label_smooth=args.label_smooth) optimizer = init_optimizer(model.parameters(), **optimizer_kwargs(args)) scheduler = lr_scheduler.MultiStepLR(optimizer, milestones=args.stepsize, gamma=args.gamma) # scheduler = lr_scheduler.ReduceLROnPlateau(optimizer, mode='min', factor=0.1, patience=3, verbose=True, threshold=1e-04) if args.load_weights and check_isfile( args.load_weights ): # load pretrained weights but ignore layers that don't match in size checkpoint = torch.load(args.load_weights) pretrain_dict = checkpoint['state_dict'] model_dict = model.state_dict() pretrain_dict = { k: v for k, v in pretrain_dict.items() if k in model_dict and model_dict[k].size() == v.size() } model_dict.update(pretrain_dict) model.load_state_dict(model_dict) print("Loaded pretrained weights from '{}'".format(args.load_weights)) if args.resume and check_isfile(args.resume): checkpoint = torch.load(args.resume) model.load_state_dict(checkpoint['state_dict']) args.start_epoch = checkpoint['epoch'] + 1 print("Loaded checkpoint from '{}'".format(args.resume)) print("- start_epoch: {}\n- rank1: {}".format(args.start_epoch, checkpoint['rank1'])) if use_gpu: model = nn.DataParallel(model).cuda() if args.evaluate: print("Evaluate only") for name in args.target_names: print("Evaluating {} ...".format(name)) queryloader = testloader_dict[name]['query'] galleryloader = testloader_dict[name]['gallery'] test_set = dm.return_testdataset_by_name(name) rank1, mAP = test(model, test_set, name, queryloader, galleryloader, use_gpu, visualize=args.visualize_ranks) return start_time = time.time() ranklogger = RankLogger(args.source_names, args.target_names) maplogger = RankLogger(args.source_names, args.target_names) train_time = 0 print("=> Start training") if args.fixbase_epoch > 0: print( "Train {} for {} epochs while keeping other layers frozen".format( args.open_layers, args.fixbase_epoch)) initial_optim_state = optimizer.state_dict() for epoch in range(args.fixbase_epoch): start_train_time = time.time() loss, prec1 = train(epoch, model, criterion, optimizer, trainloader, use_gpu, fixbase=True) print( 'Epoch: [{:02d}] [Average Loss:] {:.4f}\t [Average Prec.:] {:.2%}' .format(epoch + 1, loss, prec1)) train_time += round(time.time() - start_train_time) print("Done. All layers are open to train for {} epochs".format( args.max_epoch)) optimizer.load_state_dict(initial_optim_state) for epoch in range(args.start_epoch, args.max_epoch): start_train_time = time.time() loss, prec1 = train(epoch, model, criterion, optimizer, trainloader, use_gpu) print( 'Epoch: [{:02d}] [Average Loss:] {:.4f}\t [Average Prec.:] {:.2%}'. format(epoch + 1, loss, prec1)) train_time += round(time.time() - start_train_time) scheduler.step() if (epoch + 1) > args.start_eval and args.eval_freq > 0 and ( epoch + 1) % args.eval_freq == 0 or (epoch + 1) == args.max_epoch: print("=> Test") for name in args.target_names: print("Evaluating {} ...".format(name)) queryloader = testloader_dict[name]['query'] galleryloader = testloader_dict[name]['gallery'] test_set = dm.return_testdataset_by_name(name) if epoch + 1 == args.max_epoch: rank1, mAP = test(model, test_set, name, queryloader, galleryloader, use_gpu, visualize=True) else: rank1, mAP = test(model, test_set, name, queryloader, galleryloader, use_gpu) ranklogger.write(name, epoch + 1, rank1) maplogger.write(name, epoch + 1, mAP) if use_gpu: state_dict = model.module.state_dict() else: state_dict = model.state_dict() save_checkpoint( { 'state_dict': state_dict, 'rank1': rank1, 'epoch': epoch, }, False, osp.join(args.save_dir, 'checkpoint_ep' + str(epoch + 1) + '.pth.tar')) # save last checkpoint save_checkpoint( { 'state_dict': state_dict, 'rank1': rank1, 'epoch': epoch, }, False, osp.join(args.save_dir, 'checkpoint_ep' + str(epoch + 1) + '.pth.tar')) elapsed = round(time.time() - start_time) elapsed = str(datetime.timedelta(seconds=elapsed)) train_time = str(datetime.timedelta(seconds=train_time)) print( "Finished. Total elapsed time (h:m:s): {}. Training time (h:m:s): {}.". format(elapsed, train_time)) ranklogger.show_summary() maplogger.show_summary()
def main(): global args set_random_seed(args.seed) if not args.use_avai_gpus: os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu_devices use_gpu = torch.cuda.is_available() if args.use_cpu: use_gpu = False log_name = 'log_test.txt' if args.evaluate else 'log_train.txt' sys.stdout = Logger(osp.join(args.save_dir, log_name)) print('==========\nArgs:{}\n=========='.format(args)) if use_gpu: print('Currently using GPU {}'.format(args.gpu_devices)) cudnn.benchmark = True else: print('Currently using CPU, however, GPU is highly recommended') print('Initializing video data manager') dm = VideoDataManager(use_gpu, **video_dataset_kwargs(args)) trainloader, testloader_dict = dm.return_dataloaders() print('Initializing model: {}'.format(args.arch)) model = models.init_model(name=args.arch, num_classes=dm.num_train_pids, loss={'xent', 'htri'}, pretrained=not args.no_pretrained, use_gpu=use_gpu) print('Model size: {:.3f} M'.format(count_num_param(model))) if args.load_weights and check_isfile(args.load_weights): load_pretrained_weights(model, args.load_weights) if args.resume and check_isfile(args.resume): checkpoint = torch.load(args.resume) model.load_state_dict(checkpoint['state_dict']) args.start_epoch = checkpoint['epoch'] + 1 best_rank1 = checkpoint['rank1'] print('Loaded checkpoint from "{}"'.format(args.resume)) print('- start_epoch: {}\n- rank1: {}'.format(args.start_epoch, best_rank1)) model = nn.DataParallel(model).cuda() if use_gpu else model criterion = CrossEntropyLoss(num_classes=dm.num_train_pids, use_gpu=use_gpu, label_smooth=args.label_smooth) criterion_htri = TripletLoss(margin=args.margin) optimizer = init_optimizer(model, **optimizer_kwargs(args)) scheduler = init_lr_scheduler(optimizer, **lr_scheduler_kwargs(args)) if args.evaluate: print('Evaluate only') for name in args.target_names: print('Evaluating {} ...'.format(name)) queryloader = testloader_dict[name]['query'] galleryloader = testloader_dict[name]['gallery'] distmat = test(model, queryloader, galleryloader, args.pool_tracklet_features, use_gpu, return_distmat=True) if args.visualize_ranks: visualize_ranked_results(distmat, dm.return_testdataset_by_name(name), save_dir=osp.join( args.save_dir, 'ranked_results', name), topk=20) return start_time = time.time() ranklogger = RankLogger(args.source_names, args.target_names) train_time = 0 print('=> Start training') if args.fixbase_epoch > 0: print( 'Train {} for {} epochs while keeping other layers frozen'.format( args.open_layers, args.fixbase_epoch)) initial_optim_state = optimizer.state_dict() for epoch in range(args.fixbase_epoch): start_train_time = time.time() train(epoch, model, criterion_xent, criterion_htri, optimizer, trainloader, use_gpu, fixbase=True) train_time += round(time.time() - start_train_time) print('Done. All layers are open to train for {} epochs'.format( args.max_epoch)) optimizer.load_state_dict(initial_optim_state) for epoch in range(args.start_epoch, args.max_epoch): start_train_time = time.time() train(epoch, model, criterion_xent, criterion_htri, optimizer, trainloader, use_gpu) train_time += round(time.time() - start_train_time) scheduler.step() if (epoch + 1) > args.start_eval and args.eval_freq > 0 and ( epoch + 1) % args.eval_freq == 0 or (epoch + 1) == args.max_epoch: print('=> Test') for name in args.target_names: print('Evaluating {} ...'.format(name)) queryloader = testloader_dict[name]['query'] galleryloader = testloader_dict[name]['gallery'] rank1 = test(model, queryloader, galleryloader, args.pool_tracklet_features, use_gpu) ranklogger.write(name, epoch + 1, rank1) save_checkpoint( { 'state_dict': model.state_dict(), 'rank1': rank1, 'epoch': epoch, }, False, osp.join(args.save_dir, 'checkpoint_ep' + str(epoch + 1) + '.pth.tar')) elapsed = round(time.time() - start_time) elapsed = str(datetime.timedelta(seconds=elapsed)) train_time = str(datetime.timedelta(seconds=train_time)) print( 'Finished. Total elapsed time (h:m:s): {}. Training time (h:m:s): {}.'. format(elapsed, train_time)) ranklogger.show_summary()
def main(): global args, criterion, testloader_dict, trainloader, use_gpu set_random_seed(args.seed) if not args.use_avai_gpus: os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu_devices use_gpu = torch.cuda.is_available() if args.use_cpu: use_gpu = False log_name = 'test.log' if args.evaluate else 'train.log' sys.stdout = Logger(osp.join(args.save_dir, log_name)) print('==========\nArgs:{}\n=========='.format(args)) if use_gpu: print('Currently using GPU {}'.format(args.gpu_devices)) cudnn.benchmark = True else: warnings.warn('Currently using CPU, however, GPU is highly recommended') print('Initializing image data manager') dm = ImageDataManager(use_gpu, **image_dataset_kwargs(args)) trainloader, testloader_dict = dm.return_dataloaders() print('Initializing model: {}'.format(args.arch)) model = models.init_model(name=args.arch, num_classes=dm.num_train_pids, loss={'xent'}, pretrained=not args.no_pretrained, use_gpu=use_gpu) print('Model size: {:.3f} M'.format(count_num_param(model))) if args.load_weights and check_isfile(args.load_weights): load_pretrained_weights(model, args.load_weights) model = nn.DataParallel(model).cuda() if use_gpu else model criterion = CrossEntropyLoss(num_classes=dm.num_train_pids, use_gpu=use_gpu, label_smooth=args.label_smooth) if args.resume and check_isfile(args.resume): args.start_epoch = resume_from_checkpoint(args.resume, model, optimizer=None) resumed = True else: resumed = False if args.evaluate: print('Evaluate only') for name in args.target_names: print('Evaluating {} ...'.format(name)) queryloader = testloader_dict[name]['query'] galleryloader = testloader_dict[name]['gallery'] distmat = test(model, queryloader, galleryloader, use_gpu, return_distmat=True) if args.visualize_ranks: visualize_ranked_results( distmat, dm.return_testdataset_by_name(name), save_dir=osp.join(args.save_dir, 'ranked_results', name), topk=20 ) return time_start = time.time() # ranklogger = RankLogger(args.source_names, args.target_names) print('=> Start training') if not resumed: train_base(model) train_RRI(model, 7) elapsed = round(time.time() - time_start) elapsed = str(datetime.timedelta(seconds=elapsed)) print('Elapsed {}'.format(elapsed))